mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-11 22:25:41 +08:00
12787996d1
feat(ingestion): mirror Go pipeline progress into the document table;
harden resume guards
- pipeline: bind the owning document via WithDocumentID; after each
TrackProgress event aggregate ingestion_task_log progress and mirror
progress/run/progress_msg back into the document table, so GET
/api/v1/datasets/{dataset_id}/documents reflects live Go pipeline
progress without a bespoke endpoint.
- canvas: extend the S3 resume guard to reject legacy no-op nodes (e.g.
ExitLoop) so component_total equals the count of progress-reporting
components and the aggregate percent can reach 100%.
- runtime/canvas: route progress through TrackProgress; add interrupt
test coverage (r3_interrupt_test.go).
- dao/entity: add IngestionTask.DocumentID column and AggregateProgress
support used by the mirror; IngestionTaskLog keeps a Checkpoint column
alongside the progress fields.
feat(deepdoc): cache DocAnalyzer inference results in Redis (1h TTL)
- Redis-backed DocAnalyzerCache decorator over inference.Client; cache
key = "ddoc:cache:<method>:" + sha256 of the JPEG-encoded image bytes
(deterministic).
- TTL = 1h; hits skip the inner HTTP call and return cached JSON; inner
errors are not cached.
refactor(deepdoc): align figure cropping with Python cropout + bounded
page caches
- CropSectionByDLA mirrors Python cropout: best-overlap DLA
figure/equation region, fallback to section bbox per page, vertical
concat on gray background.
- sliding-window page-image cache bounds peak memory to the recent
window instead of the whole PDF.
- rename DLADebug -> DLARegions across parser/chunker/tests.
refactor(parser): drop lib_type selector; align NewXxxParser with
NewPDFParser
- remove config["lib_type"] lookup and the libType param/field/switch
from all nine constructors; surface the CGO-required error at
ParseWithResult time instead of construction time; drop resolveLibType,
its test, and the four lib_type constants.
feat(utility): add a reusable workerpool for bounded concurrent
execution
- internal/utility/workerpool.go (+ tests).
refactor: translate Chinese prose comments to English in non-harness Go
files.
chore: upgrade github.com/cloudwego/eino from v0.9.9 to v0.9.12.
50 lines
1.3 KiB
Go
50 lines
1.3 KiB
Go
package pdf
|
|
|
|
import (
|
|
"context"
|
|
"image"
|
|
pdf "ragflow/internal/deepdoc/parser/pdf/type"
|
|
)
|
|
|
|
// MockDocAnalyzer returns predefined data for unit tests.
|
|
// Set an Err field to non-nil to exercise the corresponding error path.
|
|
type MockDocAnalyzer struct {
|
|
DLARegions []pdf.DLARegion
|
|
TSRCells []pdf.TSRCell
|
|
OCRBoxes []pdf.OCRBox
|
|
OCRTexts []pdf.OCRText
|
|
// Per-method error injection for testing failure paths.
|
|
DLAErr error
|
|
TSRErr error
|
|
OCRDetectErr error
|
|
OCRRecognizeErr error
|
|
|
|
Healthy bool
|
|
}
|
|
|
|
func (m *MockDocAnalyzer) DLA(_ context.Context, _ image.Image) ([]pdf.DLARegion, error) {
|
|
if m.DLAErr != nil {
|
|
return nil, m.DLAErr
|
|
}
|
|
return m.DLARegions, nil
|
|
}
|
|
func (m *MockDocAnalyzer) TSR(_ context.Context, _ image.Image) ([]pdf.TSRCell, error) {
|
|
if m.TSRErr != nil {
|
|
return nil, m.TSRErr
|
|
}
|
|
return m.TSRCells, nil
|
|
}
|
|
func (m *MockDocAnalyzer) OCRDetect(_ context.Context, _ image.Image) ([]pdf.OCRBox, error) {
|
|
if m.OCRDetectErr != nil {
|
|
return nil, m.OCRDetectErr
|
|
}
|
|
return m.OCRBoxes, nil
|
|
}
|
|
func (m *MockDocAnalyzer) OCRRecognize(_ context.Context, _ image.Image) ([]pdf.OCRText, error) {
|
|
if m.OCRRecognizeErr != nil {
|
|
return nil, m.OCRRecognizeErr
|
|
}
|
|
return m.OCRTexts, nil
|
|
}
|
|
func (m *MockDocAnalyzer) Health() bool { return m.Healthy }
|